Akademik Veri Yönetim Sistemi
12th International Conference on Industrial Engineering and Applications (Europe) (ICIEA-EU 2025), Munich, Almanya, 7 - 09 Ocak 2025, (Yayınlanmadı)
Abstract: The emergence of big data has significantly
expanded the information accessible from this data. The
extensive application of machine learning, particularly deep learning, has
enabled the derivation of meaningful insights from big data sets. Nonetheless,
end users encounter several deficiencies in the developed models, including
transparency, interpretability, and reliability. In domains where
decision-making processes are essential, such as banking, healthcare, and
autonomous systems, these shortcomings pose significant problems.
"Explainable Artificial Intelligence (XAI)," which is created to
overcome these limitations, offers a systematic way to help people comprehend
the model and its judgments as well as how to evaluate the models' consistency.
This study provides a most recent literature review on the use and benefits of
XAI in the healthcare. An example of application in healthcare is also provided
in the study, which predicts the results of interventional operations on
patients with breast cancer. The survival and mortality outcomes of breast
cancer patients after surgery are modeled using with the Random Forest
Classifier and Gradient Boosting Classifier, and these models are explained
using one of the XAI techniques, Local Interpretable Model-agnostic
Explanations (LIME). LIME is a technique used to understand the predictions of
machine learning models. It provides interpretable and locally faithful
explanations by approximating the model locally with a simpler, interpretable
model. According to the findings, applying XAI aids in gaining a deeper
comprehension of the motivation behind the model's decision-making.
Keywords: Explainable
Artificial Intelligence, Gradient Boosting Classifier, Random Forest
Classifier, LIME